© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 18716
    Prev
    Next
    INDEX
    Explanations

    words related to starting and ending events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to start and end processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phia
    -0.78
     pens
    -0.72
    é¾įå
    -0.70
    pell
    -0.69
    riend
    -0.68
    avis
    -0.67
    ynt
    -0.66
    onyms
    -0.64
    enhagen
    -0.64
     cats
    -0.64
    POSITIVE LOGITS
     countdown
    0.67
     Sequence
    0.67
    endment
    0.67
    requisites
    0.64
     sequence
    0.63
     Destination
    0.61
    enium
    0.61
     Makoto
    0.61
    adder
    0.60
     anew
    0.58
    Activations Density 0.397%

    No Known Activations